@inproceedings{zhao-etal-2024-parameter,
title = "Parameter-Efficient Transfer Learning for End-to-end Speech Translation",
author = "Zhao, Yunlong and
Wang, Kexin and
Dong, Qianqian and
Ko, Tom",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1102",
pages = "12592--12598",
abstract = "Recently, end-to-end speech translation (ST) has gained significant attention in research, but its progress is hindered by the limited availability of labeled data. To overcome this challenge, leveraging pre-trained models for knowledge transfer in ST has emerged as a promising direction. In this paper, we propose PETL-ST, which investigates parameter-efficient transfer learning for end-to-end speech translation. Our method utilizes two lightweight adaptation techniques, namely prefix and adapter, to modulate Attention and the Feed-Forward Network, respectively, while preserving the capabilities of pre-trained models. We conduct experiments on MuST-C En-De, Es, Fr, Ru datasets to evaluate the performance of our approach. The results demonstrate that PETL-ST outperforms strong baselines, achieving superior translation quality with high parameter efficiency. Moreover, our method exhibits remarkable data efficiency and significantly improves performance in low-resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2024-parameter">
<titleInfo>
<title>Parameter-Efficient Transfer Learning for End-to-end Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunlong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kexin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, end-to-end speech translation (ST) has gained significant attention in research, but its progress is hindered by the limited availability of labeled data. To overcome this challenge, leveraging pre-trained models for knowledge transfer in ST has emerged as a promising direction. In this paper, we propose PETL-ST, which investigates parameter-efficient transfer learning for end-to-end speech translation. Our method utilizes two lightweight adaptation techniques, namely prefix and adapter, to modulate Attention and the Feed-Forward Network, respectively, while preserving the capabilities of pre-trained models. We conduct experiments on MuST-C En-De, Es, Fr, Ru datasets to evaluate the performance of our approach. The results demonstrate that PETL-ST outperforms strong baselines, achieving superior translation quality with high parameter efficiency. Moreover, our method exhibits remarkable data efficiency and significantly improves performance in low-resource settings.</abstract>
<identifier type="citekey">zhao-etal-2024-parameter</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1102</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12592</start>
<end>12598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parameter-Efficient Transfer Learning for End-to-end Speech Translation
%A Zhao, Yunlong
%A Wang, Kexin
%A Dong, Qianqian
%A Ko, Tom
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhao-etal-2024-parameter
%X Recently, end-to-end speech translation (ST) has gained significant attention in research, but its progress is hindered by the limited availability of labeled data. To overcome this challenge, leveraging pre-trained models for knowledge transfer in ST has emerged as a promising direction. In this paper, we propose PETL-ST, which investigates parameter-efficient transfer learning for end-to-end speech translation. Our method utilizes two lightweight adaptation techniques, namely prefix and adapter, to modulate Attention and the Feed-Forward Network, respectively, while preserving the capabilities of pre-trained models. We conduct experiments on MuST-C En-De, Es, Fr, Ru datasets to evaluate the performance of our approach. The results demonstrate that PETL-ST outperforms strong baselines, achieving superior translation quality with high parameter efficiency. Moreover, our method exhibits remarkable data efficiency and significantly improves performance in low-resource settings.
%U https://aclanthology.org/2024.lrec-main.1102
%P 12592-12598
Markdown (Informal)
[Parameter-Efficient Transfer Learning for End-to-end Speech Translation](https://aclanthology.org/2024.lrec-main.1102) (Zhao et al., LREC-COLING 2024)
ACL